{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E365XTRDICRCNC6QVOPU5W3FH7","short_pith_number":"pith:E365XTRD","canonical_record":{"source":{"id":"2409.12599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T09:24:36Z","cross_cats_sorted":[],"title_canon_sha256":"e9c419dff596b2076587bd4f1931ceebe9eda1659af92d4bfaf5a4861c56d093","abstract_canon_sha256":"cd380f8a4f0e8ae0c9fd181df40cb4203722b82c905a58bf62df6b760635ed17"},"schema_version":"1.0"},"canonical_sha256":"26fddbce2340a2268bd0ab9f4edb653fc81e2b97280abe689411eb2feeee1e0c","source":{"kind":"arxiv","id":"2409.12599","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12599","created_at":"2026-07-05T09:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12599v1","created_at":"2026-07-05T09:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12599","created_at":"2026-07-05T09:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"E365XTRDICRC","created_at":"2026-07-05T09:09:09Z"},{"alias_kind":"pith_short_16","alias_value":"E365XTRDICRCNC6Q","created_at":"2026-07-05T09:09:09Z"},{"alias_kind":"pith_short_8","alias_value":"E365XTRD","created_at":"2026-07-05T09:09:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E365XTRDICRCNC6QVOPU5W3FH7","target":"record","payload":{"canonical_record":{"source":{"id":"2409.12599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T09:24:36Z","cross_cats_sorted":[],"title_canon_sha256":"e9c419dff596b2076587bd4f1931ceebe9eda1659af92d4bfaf5a4861c56d093","abstract_canon_sha256":"cd380f8a4f0e8ae0c9fd181df40cb4203722b82c905a58bf62df6b760635ed17"},"schema_version":"1.0"},"canonical_sha256":"26fddbce2340a2268bd0ab9f4edb653fc81e2b97280abe689411eb2feeee1e0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:09.456126Z","signature_b64":"DVX2NBxiBMvzxNGocCrj1PJU2LswM1CIUgT51qbMOv7HlZ2UjC/HEz0//R6KAJXY3Thz5wDrIG6nvI5r/0vRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26fddbce2340a2268bd0ab9f4edb653fc81e2b97280abe689411eb2feeee1e0c","last_reissued_at":"2026-07-05T09:09:09.455699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:09.455699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.12599","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IWZwgLcIwkfUOnwg4zwBwtngf2JvLMiSkxeNETRlNmk0xz62/LOiY+f2wP8IAdopg+9BColOrpxY8xDpz3MeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:40:36.418299Z"},"content_sha256":"c678fbca4ecbeacbce1b7c97ff18a12364b728205330787dad6637a7ae77f53b","schema_version":"1.0","event_id":"sha256:c678fbca4ecbeacbce1b7c97ff18a12364b728205330787dad6637a7ae77f53b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E365XTRDICRCNC6QVOPU5W3FH7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing SLM via ChatGPT and Dataset Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gunther Heidemann, Kai-Uwe K\\\"uhnberger, Mohamad Ballout, Tom Pieper, Ulf Krumnack","submitted_at":"2024-09-19T09:24:36Z","abstract_excerpt":"This paper explores the enhancement of small language models through strategic dataset augmentation via ChatGPT-3.5-Turbo, in the domain of Natural Language Inference (NLI). By employing knowledge distillation-based techniques and synthetic dataset augmentation, we aim to bridge the performance gap between large language models (LLMs) and small language models (SLMs) without the immense cost of human annotation. Our methods involve two forms of rationale generation--information extraction and informed reasoning--to enrich the ANLI dataset. We then fine-tune T5-Small on these augmented datasets"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12599","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.12599/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3bSyLRt/xqRxHYK8yTButD67XE1+Sq7Ib0OS63KuzvZZlqbHlyUsu+SNmeEA8iEDQEuoPO9ETRdptxpaIj0iCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:40:36.418909Z"},"content_sha256":"b68ad8ad03b5de1121af04447ee9dd0960141dfa32a3b70b8f3bd45fc9b04c50","schema_version":"1.0","event_id":"sha256:b68ad8ad03b5de1121af04447ee9dd0960141dfa32a3b70b8f3bd45fc9b04c50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E365XTRDICRCNC6QVOPU5W3FH7/bundle.json","state_url":"https://pith.science/pith/E365XTRDICRCNC6QVOPU5W3FH7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E365XTRDICRCNC6QVOPU5W3FH7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T06:40:36Z","links":{"resolver":"https://pith.science/pith/E365XTRDICRCNC6QVOPU5W3FH7","bundle":"https://pith.science/pith/E365XTRDICRCNC6QVOPU5W3FH7/bundle.json","state":"https://pith.science/pith/E365XTRDICRCNC6QVOPU5W3FH7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E365XTRDICRCNC6QVOPU5W3FH7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E365XTRDICRCNC6QVOPU5W3FH7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cd380f8a4f0e8ae0c9fd181df40cb4203722b82c905a58bf62df6b760635ed17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T09:24:36Z","title_canon_sha256":"e9c419dff596b2076587bd4f1931ceebe9eda1659af92d4bfaf5a4861c56d093"},"schema_version":"1.0","source":{"id":"2409.12599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12599","created_at":"2026-07-05T09:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12599v1","created_at":"2026-07-05T09:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12599","created_at":"2026-07-05T09:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"E365XTRDICRC","created_at":"2026-07-05T09:09:09Z"},{"alias_kind":"pith_short_16","alias_value":"E365XTRDICRCNC6Q","created_at":"2026-07-05T09:09:09Z"},{"alias_kind":"pith_short_8","alias_value":"E365XTRD","created_at":"2026-07-05T09:09:09Z"}],"graph_snapshots":[{"event_id":"sha256:b68ad8ad03b5de1121af04447ee9dd0960141dfa32a3b70b8f3bd45fc9b04c50","target":"graph","created_at":"2026-07-05T09:09:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.12599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores the enhancement of small language models through strategic dataset augmentation via ChatGPT-3.5-Turbo, in the domain of Natural Language Inference (NLI). By employing knowledge distillation-based techniques and synthetic dataset augmentation, we aim to bridge the performance gap between large language models (LLMs) and small language models (SLMs) without the immense cost of human annotation. Our methods involve two forms of rationale generation--information extraction and informed reasoning--to enrich the ANLI dataset. We then fine-tune T5-Small on these augmented datasets","authors_text":"Gunther Heidemann, Kai-Uwe K\\\"uhnberger, Mohamad Ballout, Tom Pieper, Ulf Krumnack","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T09:24:36Z","title":"Enhancing SLM via ChatGPT and Dataset Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12599","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c678fbca4ecbeacbce1b7c97ff18a12364b728205330787dad6637a7ae77f53b","target":"record","created_at":"2026-07-05T09:09:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cd380f8a4f0e8ae0c9fd181df40cb4203722b82c905a58bf62df6b760635ed17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T09:24:36Z","title_canon_sha256":"e9c419dff596b2076587bd4f1931ceebe9eda1659af92d4bfaf5a4861c56d093"},"schema_version":"1.0","source":{"id":"2409.12599","kind":"arxiv","version":1}},"canonical_sha256":"26fddbce2340a2268bd0ab9f4edb653fc81e2b97280abe689411eb2feeee1e0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26fddbce2340a2268bd0ab9f4edb653fc81e2b97280abe689411eb2feeee1e0c","first_computed_at":"2026-07-05T09:09:09.455699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:09.455699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DVX2NBxiBMvzxNGocCrj1PJU2LswM1CIUgT51qbMOv7HlZ2UjC/HEz0//R6KAJXY3Thz5wDrIG6nvI5r/0vRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:09.456126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c678fbca4ecbeacbce1b7c97ff18a12364b728205330787dad6637a7ae77f53b","sha256:b68ad8ad03b5de1121af04447ee9dd0960141dfa32a3b70b8f3bd45fc9b04c50"],"state_sha256":"bf15a6d3f9372468b2a040cccaa00ac41cce8eacebf4fe4eeaa9ebeb6b3e30ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FFpN4AsXTxiYO/yxjtqqi2wEz1nZeyxSeEHjk5Pbo+C5HMxLYHlclLuyGwcmKT/GFGecXi6SESpnC7+JG5epCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:40:36.422632Z","bundle_sha256":"f643e98c41bed63541ed303abd5c9ec27d01d89c9568001c6c0c1f7ee0a203f8"}}